Benchmark result

qwen3.8:27b-q4_K_M on 2× AMD Radeon RX 7800 XT — 27.0 tok/s

Measured with Ollama 0.40.1 on October 9, 2026.

What the model built

The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.

How this run compares

qwen3.8:27b-q4_K_M on other hardware

35.8tok/s86.5AMD Radeon RX 7900 XTX · Q4_K_M
33.2tok/s85.1AMD Radeon RX 7900 XTX · Q4_K_M

Reproduce this run

toolOllama 0.40.1

modelqwen3.8:27b-q4_K_M (Q4_K_M)

context65,536

thinkingon

samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1

clientv0.4.89+102

Set those in Ollama, then:

llm-benchmark benchmark --model "qwen3.8:27b-q4_K_M" --tool "Ollama"

The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.